Anomaly detection in real-time gross payment data

Ron Triepels, Hennie Daniels, R. Heijmans

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

We discuss how an autoencoder can detect system-level anomalies in a real-time gross settlement system by reconstructing a set of liquidity vectors. A liquidity vector is an aggregated representation of the underlying payment network of a settlement system for a particular time interval. Furthermore, we evaluate the performance of two autoencoders on real-world payment data extracted from the TARGET2 settlement system. We do this by generating different types of artificial bank runs in the data and determining how the autoencoders respond. Our experimental results show that the autoencoders are able to detect unexpected changes in the liquidity flows between banks.
Original languageEnglish
Title of host publicationProceedings of the 19th International Conference on Enterprise Information Systems (ICEIS 2017)
EditorsOlivier Camp, Joaquim Filipe
PublisherSciTePress
Pages433-441
ISBN (Print)9789897282479
DOIs
Publication statusPublished - 2017
Event19th International Conference on Enterprise Information Systems - Porto, Portugal
Duration: 26 Apr 201729 Apr 2017

Conference

Conference19th International Conference on Enterprise Information Systems
Abbreviated titleICEIS 2017
CountryPortugal
CityPorto
Period26/04/1729/04/17

    Fingerprint

Keywords

  • anomaly detection
  • neural network
  • autoencoder
  • real-time gross settlement system

Cite this

Triepels, R., Daniels, H., & Heijmans, R. (2017). Anomaly detection in real-time gross payment data. In O. Camp, & J. Filipe (Eds.), Proceedings of the 19th International Conference on Enterprise Information Systems (ICEIS 2017) (pp. 433-441). SciTePress. https://doi.org/10.5220/0006333004330441